Power management and ACPI material for 3.19-rc3

- Fix for a potential NULL pointer dereference in the cpufreq
    core due to an initialization race condition (Ethan Zhao).
 
  - Fixes for abuse of the OPP (Operating Performance Points) API
    related to RCU and other minor issues in the OPP library and
    the cpufreq-dt driver (Dmitry Torokhov).
 
  - cpuidle governors cleanup making them measure idle duration in
    a better way without using the CPUIDLE_FLAG_TIME_INVALID flag
    which allows that flag to be dropped from the ACPI cpuidle driver
    and from the core too (Len Brown).
 
  - New ACPI backlight blacklist entries for Samsung machines
    without a working native backlight interface that need to
    use the ACPI backlight instead (Aaron Lu).
 
  - New CPU IDs of future Intel Xeon CPUs for the Intel RAPL power
    capping driver (Jacob Pan).
 
  - Generic power domains framework modification to export the
    of_genpd_get_from_provider() function to modular drivers that
    will allow future driver modifications to be based on the mainline
    (Amit Daniel Kachhap).
 
  - Two fixes for the cpupower tool (Michal Privoznik, Prarit Bhargava).
 
 /
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v2.0.22 (GNU/Linux)
 
 iQIcBAABCAAGBQJUoccdAAoJEILEb/54YlRxP9IQAJIAz5RSRQpv50nq+oMLER/S
 G4FrVRgELYNTCvujlsgTydSa2IP/G4bPfa7zMquIs69j0L4/65z5aDAMNfHMiNQy
 6ZC1Vey7mS+A91pdhhkI3MZ9GIu/HIBnXdhhzQaVOTFG+X8Ro+9WZva6fzgqhw3p
 hhtjdNkiURoul+uGL0/tk/Ia228gn0Evw+DiPxH+6TyuR2Nzuolc1mKBqE4n948l
 e99U3SPqT2/fH4otYKXKgz60NldRu9EjBtjSanLRlSEHw8NXI/fbaQJ/YUPL8qnT
 gfvm694nhU7lERG4jhKMIdx2ubeMpjyRLbgDu+8XmAyMUik9nHfFG5wC04V6vSP5
 0JgJyFfXT0HjcvHf1EyFZ5zvqy5FrRUV81E0MXz1Yi14E/MiBvUyNz+ThTQ+7VYT
 MIdFcqo7hSOjXFjMU6orkxGWqJQpKz2I4BBuQikvCnHQxkevscRS8G0SpxLp6nyD
 dFBQBZgztZc0FbqlQINszPOa7FXwL042nk9+YobEyE9i3v7lC8zMwNtAav76LSTd
 Z0/OivQziIwyNxIjrNkTXGnqhxXwKGMQ/JOywaswos7MdnCS2B9sRgn9zCZZ0JSs
 Z59gAli3A0/qv7YiWy8jxEkL8uqeNu1PCmiwlVuEl15/p+C9w+t4iFJi9DiGFXiF
 sJOZmy1GcmQCGr9m+qA0
 =CYBE
 -----END PGP SIGNATURE-----

Merge tag 'pm+acpi-3.19-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management and ACPI material from Rafael J Wysocki:
 "These are fixes (operating performance points library, cpufreq-dt
  driver, cpufreq core, ACPI backlight, cpupower tool), cleanups
  (cpuidle), new processor IDs for the RAPL (Running Average Power
  Limit) power capping driver, and a modification of the generic power
  domains framework allowing modular drivers to call one of its helper
  functions.

  Specifics:

   - Fix for a potential NULL pointer dereference in the cpufreq core
     due to an initialization race condition (Ethan Zhao).

   - Fixes for abuse of the OPP (Operating Performance Points) API
     related to RCU and other minor issues in the OPP library and the
     cpufreq-dt driver (Dmitry Torokhov).

   - cpuidle governors cleanup making them measure idle duration in a
     better way without using the CPUIDLE_FLAG_TIME_INVALID flag which
     allows that flag to be dropped from the ACPI cpuidle driver and
     from the core too (Len Brown).

   - New ACPI backlight blacklist entries for Samsung machines without a
     working native backlight interface that need to use the ACPI
     backlight instead (Aaron Lu).

   - New CPU IDs of future Intel Xeon CPUs for the Intel RAPL power
     capping driver (Jacob Pan).

   - Generic power domains framework modification to export the
     of_genpd_get_from_provider() function to modular drivers that will
     allow future driver modifications to be based on the mainline (Amit
     Daniel Kachhap).

   - Two fixes for the cpupower tool (Michal Privoznik, Prarit
     Bhargava)"

* tag 'pm+acpi-3.19-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
  ACPI / video: Add some Samsung models to disable_native_backlight list
  tools / cpupower: Fix no idle state information return value
  tools / cpupower: Correctly detect if running as root
  cpufreq: fix a NULL pointer dereference in __cpufreq_governor()
  cpufreq-dt: defer probing if OPP table is not ready
  PM / OPP: take RCU lock in dev_pm_opp_get_opp_count
  PM / OPP: fix warning in of_free_opp_table()
  PM / OPP: add some lockdep annotations
  powercap / RAPL: add IDs for future Xeon CPUs
  PM / Domains: Export of_genpd_get_from_provider function
  cpuidle / ACPI: remove unused CPUIDLE_FLAG_TIME_INVALID
  cpuidle: ladder: Better idle duration measurement without using CPUIDLE_FLAG_TIME_INVALID
  cpuidle: menu: Better idle duration measurement without using CPUIDLE_FLAG_TIME_INVALID

drivers/acpi/processor_idle.c

@@ -985,8 +985,6 @@ static int acpi_processor_setup_cpuidle_states(struct acpi_processor *pr)
 		state->flags = 0;
 		switch (cx->type) {
 			case ACPI_STATE_C1:
-			if (cx->entry_method != ACPI_CSTATE_FFH)
-				state->flags |= CPUIDLE_FLAG_TIME_INVALID;
 
 			state->enter = acpi_idle_enter_c1;
 			state->enter_dead = acpi_idle_play_dead;

drivers/acpi/video.c

@@ -505,6 +505,23 @@ static struct dmi_system_id video_dmi_table[] __initdata = {
 		DMI_MATCH(DMI_PRODUCT_NAME, "HP ENVY 15 Notebook PC"),
 		},
 	},
+
+	{
+	 .callback = video_disable_native_backlight,
+	 .ident = "SAMSUNG 870Z5E/880Z5E/680Z5E",
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."),
+		DMI_MATCH(DMI_PRODUCT_NAME, "870Z5E/880Z5E/680Z5E"),
+		},
+	},
+	{
+	 .callback = video_disable_native_backlight,
+	 .ident = "SAMSUNG 370R4E/370R4V/370R5E/3570RE/370R5V",
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."),
+		DMI_MATCH(DMI_PRODUCT_NAME, "370R4E/370R4V/370R5E/3570RE/370R5V"),
+		},
+	},
 	{}
 };
 

drivers/base/power/domain.c

@@ -2088,7 +2088,7 @@ EXPORT_SYMBOL_GPL(of_genpd_del_provider);
  * Returns a valid pointer to struct generic_pm_domain on success or ERR_PTR()
  * on failure.
  */
-static struct generic_pm_domain *of_genpd_get_from_provider(
+struct generic_pm_domain *of_genpd_get_from_provider(
 					struct of_phandle_args *genpdspec)
 {
 	struct generic_pm_domain *genpd = ERR_PTR(-ENOENT);
@@ -2108,6 +2108,7 @@ static struct generic_pm_domain *of_genpd_get_from_provider(
 
 	return genpd;
 }
+EXPORT_SYMBOL_GPL(of_genpd_get_from_provider);
 
 /**
  * genpd_dev_pm_detach - Detach a device from its PM domain.

drivers/base/power/opp.c

@@ -108,6 +108,14 @@ static LIST_HEAD(dev_opp_list);
 /* Lock to allow exclusive modification to the device and opp lists */
 static DEFINE_MUTEX(dev_opp_list_lock);
 
+#define opp_rcu_lockdep_assert()					\
+do {									\
+	rcu_lockdep_assert(rcu_read_lock_held() ||			\
+				lockdep_is_held(&dev_opp_list_lock),	\
+			   "Missing rcu_read_lock() or "		\
+			   "dev_opp_list_lock protection");		\
+} while (0)
+
 /**
  * find_device_opp() - find device_opp struct using device pointer
  * @dev:	device pointer used to lookup device OPPs
@@ -208,9 +216,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_freq);
  * This function returns the number of available opps if there are any,
  * else returns 0 if none or the corresponding error value.
  *
- * Locking: This function must be called under rcu_read_lock(). This function
+ * Locking: This function takes rcu_read_lock().
- * internally references two RCU protected structures: device_opp and opp which
- * are safe as long as we are under a common RCU locked section.
  */
 int dev_pm_opp_get_opp_count(struct device *dev)
 {
@@ -218,11 +224,14 @@ int dev_pm_opp_get_opp_count(struct device *dev)
 	struct dev_pm_opp *temp_opp;
 	int count = 0;
 
+	rcu_read_lock();
+
 	dev_opp = find_device_opp(dev);
 	if (IS_ERR(dev_opp)) {
-		int r = PTR_ERR(dev_opp);
+		count = PTR_ERR(dev_opp);
-		dev_err(dev, "%s: device OPP not found (%d)\n", __func__, r);
+		dev_err(dev, "%s: device OPP not found (%d)\n",
-		return r;
+			__func__, count);
+		goto out_unlock;
 	}
 
 	list_for_each_entry_rcu(temp_opp, &dev_opp->opp_list, node) {
@@ -230,6 +239,8 @@ int dev_pm_opp_get_opp_count(struct device *dev)
 			count++;
 	}
 
+out_unlock:
+	rcu_read_unlock();
 	return count;
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_get_opp_count);
@@ -267,6 +278,8 @@ struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev,
 	struct device_opp *dev_opp;
 	struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ERANGE);
 
+	opp_rcu_lockdep_assert();
+
 	dev_opp = find_device_opp(dev);
 	if (IS_ERR(dev_opp)) {
 		int r = PTR_ERR(dev_opp);
@@ -313,6 +326,8 @@ struct dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev,
 	struct device_opp *dev_opp;
 	struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ERANGE);
 
+	opp_rcu_lockdep_assert();
+
 	if (!dev || !freq) {
 		dev_err(dev, "%s: Invalid argument freq=%p\n", __func__, freq);
 		return ERR_PTR(-EINVAL);
@@ -361,6 +376,8 @@ struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev,
 	struct device_opp *dev_opp;
 	struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ERANGE);
 
+	opp_rcu_lockdep_assert();
+
 	if (!dev || !freq) {
 		dev_err(dev, "%s: Invalid argument freq=%p\n", __func__, freq);
 		return ERR_PTR(-EINVAL);
@@ -783,9 +800,15 @@ void of_free_opp_table(struct device *dev)
 
 	/* Check for existing list for 'dev' */
 	dev_opp = find_device_opp(dev);
-	if (WARN(IS_ERR(dev_opp), "%s: dev_opp: %ld\n", dev_name(dev),
+	if (IS_ERR(dev_opp)) {
-		 PTR_ERR(dev_opp)))
+		int error = PTR_ERR(dev_opp);
+		if (error != -ENODEV)
+			WARN(1, "%s: dev_opp: %d\n",
+			     IS_ERR_OR_NULL(dev) ?
+					"Invalid device" : dev_name(dev),
+			     error);
 		return;
+	}
 
 	/* Hold our list modification lock here */
 	mutex_lock(&dev_opp_list_lock);

drivers/cpufreq/cpufreq-dt.c

@@ -211,6 +211,17 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 	/* OPPs might be populated at runtime, don't check for error here */
 	of_init_opp_table(cpu_dev);
 
+	/*
+	 * But we need OPP table to function so if it is not there let's
+	 * give platform code chance to provide it for us.
+	 */
+	ret = dev_pm_opp_get_opp_count(cpu_dev);
+	if (ret <= 0) {
+		pr_debug("OPP table is not ready, deferring probe\n");
+		ret = -EPROBE_DEFER;
+		goto out_free_opp;
+	}
+
 	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
 	if (!priv) {
 		ret = -ENOMEM;

drivers/cpufreq/cpufreq.c

@@ -2028,6 +2028,12 @@ static int __cpufreq_governor(struct cpufreq_policy *policy,
 	/* Don't start any governor operations if we are entering suspend */
 	if (cpufreq_suspended)
 		return 0;
+	/*
+	 * Governor might not be initiated here if ACPI _PPC changed
+	 * notification happened, so check it.
+	 */
+	if (!policy->governor)
+		return -EINVAL;
 
 	if (policy->governor->max_transition_latency &&
 	    policy->cpuinfo.transition_latency >

drivers/cpuidle/governors/ladder.c

@@ -79,12 +79,7 @@ static int ladder_select_state(struct cpuidle_driver *drv,
 
 	last_state = &ldev->states[last_idx];
 
-	if (!(drv->states[last_idx].flags & CPUIDLE_FLAG_TIME_INVALID)) {
+	last_residency = cpuidle_get_last_residency(dev) - drv->states[last_idx].exit_latency;
-		last_residency = cpuidle_get_last_residency(dev) - \
-					 drv->states[last_idx].exit_latency;
-	}
-	else
-		last_residency = last_state->threshold.promotion_time + 1;
 
 	/* consider promotion */
 	if (last_idx < drv->state_count - 1 &&

drivers/cpuidle/governors/menu.c

@@ -396,8 +396,8 @@ static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 	 * power state and occurrence of the wakeup event.
 	 *
 	 * If the entered idle state didn't support residency measurements,
-	 * we are basically lost in the dark how much time passed.
+	 * we use them anyway if they are short, and if long,
-	 * As a compromise, assume we slept for the whole expected time.
+	 * truncate to the whole expected time.
 	 *
 	 * Any measured amount of time will include the exit latency.
 	 * Since we are interested in when the wakeup begun, not when it
@@ -405,23 +405,18 @@ static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 	 * the measured amount of time is less than the exit latency,
 	 * assume the state was never reached and the exit latency is 0.
 	 */
-	if (unlikely(target->flags & CPUIDLE_FLAG_TIME_INVALID)) {
+
-		/* Use timer value as is */
+	/* measured value */
+	measured_us = cpuidle_get_last_residency(dev);
+
+	/* Deduct exit latency */
+	if (measured_us > target->exit_latency)
+		measured_us -= target->exit_latency;
+
+	/* Make sure our coefficients do not exceed unity */
+	if (measured_us > data->next_timer_us)
 		measured_us = data->next_timer_us;
 
-	} else {
-		/* Use measured value */
-		measured_us = cpuidle_get_last_residency(dev);
-
-		/* Deduct exit latency */
-		if (measured_us > target->exit_latency)
-			measured_us -= target->exit_latency;
-
-		/* Make sure our coefficients do not exceed unity */
-		if (measured_us > data->next_timer_us)
-			measured_us = data->next_timer_us;
-	}
-
 	/* Update our correction ratio */
 	new_factor = data->correction_factor[data->bucket];
 	new_factor -= new_factor / DECAY;

drivers/powercap/intel_rapl.c

@@ -1041,6 +1041,7 @@ static const struct x86_cpu_id rapl_ids[] = {
 	RAPL_CPU(0x45, rapl_defaults_core),/* Haswell ULT */
 	RAPL_CPU(0x4C, rapl_defaults_atom),/* Braswell */
 	RAPL_CPU(0x4A, rapl_defaults_atom),/* Tangier */
+	RAPL_CPU(0x56, rapl_defaults_core),/* Future Xeon */
 	RAPL_CPU(0x5A, rapl_defaults_atom),/* Annidale */
 	{}
 };

include/linux/cpuidle.h

@@ -53,7 +53,6 @@ struct cpuidle_state {
 };
 
 /* Idle State Flags */
-#define CPUIDLE_FLAG_TIME_INVALID	(0x01) /* is residency time measurable? */
 #define CPUIDLE_FLAG_COUPLED	(0x02) /* state applies to multiple cpus */
 #define CPUIDLE_FLAG_TIMER_STOP (0x04)  /* timer is stopped on this state */
 
@@ -89,8 +88,6 @@ DECLARE_PER_CPU(struct cpuidle_device, cpuidle_dev);
 /**
  * cpuidle_get_last_residency - retrieves the last state's residency time
  * @dev: the target CPU
- *
- * NOTE: this value is invalid if CPUIDLE_FLAG_TIME_INVALID is set
  */
 static inline int cpuidle_get_last_residency(struct cpuidle_device *dev)
 {

include/linux/pm_domain.h

@@ -271,6 +271,8 @@ typedef struct generic_pm_domain *(*genpd_xlate_t)(struct of_phandle_args *args,
 int __of_genpd_add_provider(struct device_node *np, genpd_xlate_t xlate,
 			void *data);
 void of_genpd_del_provider(struct device_node *np);
+struct generic_pm_domain *of_genpd_get_from_provider(
+			struct of_phandle_args *genpdspec);
 
 struct generic_pm_domain *__of_genpd_xlate_simple(
 					struct of_phandle_args *genpdspec,
@@ -288,6 +290,12 @@ static inline int __of_genpd_add_provider(struct device_node *np,
 }
 static inline void of_genpd_del_provider(struct device_node *np) {}
 
+static inline struct generic_pm_domain *of_genpd_get_from_provider(
+			struct of_phandle_args *genpdspec)
+{
+	return NULL;
+}
+
 #define __of_genpd_xlate_simple		NULL
 #define __of_genpd_xlate_onecell	NULL
 

tools/power/cpupower/utils/cpupower.c

@@ -199,7 +199,7 @@ int main(int argc, const char *argv[])
 	}
 
 	get_cpu_info(0, &cpupower_cpu_info);
-	run_as_root = !getuid();
+	run_as_root = !geteuid();
 	if (run_as_root) {
 		ret = uname(&uts);
 		if (!ret && !strcmp(uts.machine, "x86_64") &&

tools/power/cpupower/utils/helpers/sysfs.c

@@ -361,7 +361,7 @@ unsigned int sysfs_get_idlestate_count(unsigned int cpu)
 
 	snprintf(file, SYSFS_PATH_MAX, PATH_TO_CPU "cpuidle");
 	if (stat(file, &statbuf) != 0 || !S_ISDIR(statbuf.st_mode))
-		return -ENODEV;
+		return 0;
 
 	snprintf(file, SYSFS_PATH_MAX, PATH_TO_CPU "cpu%u/cpuidle/state0", cpu);
 	if (stat(file, &statbuf) != 0 || !S_ISDIR(statbuf.st_mode))